Evaluating information retrieval system performance based on user preference

One of the challenges of modern information retrieval is to rank the most relevant documents at the top of the large system output. This calls for choosing the proper methods to evaluate the system performance. The traditional performance measures, such as precision and recall, are based on binary relevance judgment and are not appropriate for multi-grade relevance. The main objective of this paper is to propose a framework for system evaluation based on user preference of documents. It is shown that the notion of user preference is general and flexible for formally defining and interpreting multi-grade relevance. We review 12 evaluation methods and compare their similarities and differences. We find that the normalized distance performance measure is a good choice in terms of the sensitivity to document rank order and gives higher credits to systems for their ability to retrieve highly relevant documents.     

Characterization of privacy based on context sensitivity and user preference for multimedia context-aware on IoT

Multimedia Tools and Applications - In an IoT environment, building a Context-Aware system is mandatory and can provide a suitable and timely (just-in-time) service suited to the context of the...     

Tuning user profiles based on analyzing dynamic preference in document retrieval systems

Modeling users’ preferences and needs is one of the most important personalization tasks in information retrieval domain. In this paper a model for user profile tuning in document retrieval systems is considered. Methods for tuning the user profile based on analysis of user preferences dynamics are experimentally evaluated to check whether with growing history of user activity the created user profile can converge to his preferences. As the statistical analysis of series of simulations has shown, proposed methods of user profile actualization are effective in the sense that the distance between user preferences and his profile becomes smaller and smaller along with time.     

考虑非对称用户偏好的推荐算法

为解决常见的相似性方法存在未考虑用户间共同评分项在目标用户所评项目中的比例以及用户评分偏好的问题。提出了非对称因子和偏好因子,用于提高用户相似性计算的准确性。在公开的MovieLens和Yahoo Music数据集上的实验表明,引入这两个因子后,相似性模型的预测误差下降显著,优于其他相似性方法。非对称因子和偏好因子的引入更合理地体现出用户间的评分差异性,有效地处理了用户偏好问题,提高了推荐质量。     

Improving recommender system via knowledge graph based exploring user preference

Applied Intelligence - Knowledge graph(KG) has proven to improve recommendation performance. However, most efforts explore inter-entity relatedness by mining multi-hop relations on KG, thus failing...     

基于用户偏好和可疑度的推荐方法研究

针对传统推荐算法在推荐过程中存在忽略用户偏好、用户恶意虚假信息和时间序列等问题,本文引入用户兴趣模型,结合用户可疑度与时间效应计算更新用户相似度,经过深度学习网络得到最佳推荐目标。为避免出现数据过拟合情况,在利用贪心思想训练用户数据时,给隐含层和可见层均加上了用户偏好,一定程度上提高深度学习网络的自学习能力。将改进的算法与传统协同过滤推荐算法在Movie Lens 数据集上做推荐对比实验,实验证明：相对于传统的推荐算法,改进的推荐算法可以大大提高项目推荐的精确度。     

Collision-free human-robot collaboration based on context awareness

Recent advancements in human-robot collaboration have enabled human operators and robots to work together in a shared manufacturing environment. However, current distance-based collision-free human-robot collaboration system can only ensure human safety but not assembly efficiency. In this paper, the authors present a context awareness-based collision-free human-robot collaboration system that can provide human safety and assembly efficiency at the same time. The system can plan robotic paths that avoid colliding with human operators while still reach target positions in time. Human operators’ poses can also be recognised with low computational expenses to further improve assembly efficiency. To support the context-aware collision-free system, a complete collision sensing module with sensor calibration algorithms is proposed and implemented. An efficient transfer learning-based human pose recognition algorithm is also adapted and tested. Two experiments are designed to test the performance of the proposed human pose recognition algorithm and the overall system. The results indicate an efficiency improvement of the overall system.     

A multi-agent based user context Bayesian neural network analysis system

The increasing user mobility demands placed upon IT services necessitates an environment that enables users to access optimal services at any time and in any place. This study presents research conducted to develop a system that is capable of analyzing user IT service patterns and tendencies and provides the necessary service resources by sharing each user’s context information. First, each user’s context information is gathered to provide the multi-agent software training data necessary to describe user operations in a hybrid peer-to-peer (P2P) structured communication environment. Next, the data collected about each user’s mobile device is analyzed through a Bayesian based neural network system to identify the user’s tendency and extract essential service information. This information provides a communication configuration allowing the user access to the best communication service between the user’s mobile device and the local server at any time and in any place, thereby enhancing the ubiquitous computing environment.     

结合用户聚类和评分偏好的推荐算法*

针对推荐算法中用户评分矩阵维度高、计算量大的问题,为更加真实地反映用户本身评分偏好,提出一种结合用户聚类和评分偏好的推荐算法。先利用PCA降维和k-means聚类对用户评分矩阵进行预处理,在最近邻选取方法上,添加用户共同评分数量作为约束,利用用户和相似簇的相似度对相似簇内评分加权求和生成基本预测评分;再综合用户评分偏置和用户项目类型偏好,建立用户评分偏好模型;最后通过多元线性回归确定每部分的权重,生成最终的预测评分。对比实验结果表明,新算法能更真实地反映用户评分,有效减少计算量并提高推荐系统的预测准确率,更好地满足用户对于推荐系统的个性化需求。     

基于用户潜在时效偏好的推荐算法*

针对推荐系统中用户兴趣的潜在性以及高时效性业务场景下用户兴趣的不稳定性和时间迁移性进行研究,提出一种基于用户潜在时效偏好的推荐方法。通过深入分析用户的历史行为与用户潜在兴趣的关系,提出基于概率主题模型的用户兴趣挖掘方法,避免了传统推荐方式对用户兴趣潜在性的忽略;同时,基于高时效业务对时间敏感性的考虑,结合隐马尔科夫模型对用户兴趣进行实时捕获,发现用户的兴趣迁移序列,并以此提出基于用户时效偏好的推荐方法。最后通过相关实验验证了所提出方法的可行性。     

Adaptive hypertext navigation based on user goals and context

Hypertext systems allow flexible access to topics of information, but this flexibility has disadvantages. Users often become lost or overwhelmed by choices. An adaptive hypertext system can overcome these disadvantages by recommending information to users based on their specific information needs and preferences. Simple associative matrices provide an effective way of capturing these user preferences. Because the matrices are easily updated, they support the kind of dynamic learning required in an adaptive system.HYPERFLEX, a prototype of an adaptive hypertext system that learns, is described. Informal studies with HYPERFLEX clarify the circumstances under which adaptive systems are likely to be useful, and suggest that HYPERFLEX can reduce time spent searching for information by up to 40%. Moreover, these benefits can be obtained with relatively little effort on the part of hypertext authors or users.The simple models underlying HYPERFLEX's performance may offer a general and useful alternative to more sophisticated modelling techniques. Conditions under which these models, and similar adaptation techniques, might be most useful are discussed.     

基于用户偏好与副本阈值的端到端缓存算法

在端到端（D2D）缓存网络中存在大量多媒体内容，而移动终端中缓存空间却相对有限。为了实现移动终端中缓存空间的高效利用，提出了一种基于用户偏好与副本阈值的D2D缓存部署算法。首先，基于用户偏好，设计缓存收益函数，用于判断各文件的缓存价值；然后，以系统缓存命中率最大化为目标，利用凸规划理论设计缓存副本阈值，用于部署系统中文件的副本数量；最后，联合缓存收益函数与副本阈值，提出一种启发式算法实现了文件的缓存部署。与现有缓存部署算法相比，该算法可显著提升缓存命中率及卸载增益，降低服务时延。     

A study on user preference of high dynamic range over low dynamic range video

The increased interest in high dynamic range (HDR) video over existing low dynamic range (LDR) video during the past decade or so was primarily due to its inherent capability to capture, store and display the full range of real-world lighting visible to the human eye with increased precision. This has led to an inherent assumption that HDR video would be preferable by the end-user over LDR video due to the more immersive and realistic visual experience provided by HDR. This assumption has led to a considerable body of research into efficient capture, processing, storage and display of HDR video. Although this is beneficial for scientific research and industrial purposes, very little research has been conducted to test the veracity of this assumption. In this paper, we conduct two subjective studies by means of a ranking and a rating-based experiment where 60 participants in total, 30 in each experiment, were tasked to rank and rate several reference HDR video scenes along with three mapped LDR versions of each scene on an HDR display, in order of their viewing preference. Results suggest that given the option, end-users prefer the HDR representation of the scene over its LDR counterpart.     

基于评论挖掘和用户偏好学习的评分预测协同过滤*

提出了一种新的方法挖掘评论中的文字信息,将评论对象被用户关注的层面发掘出来并评分,根据这些层面的分数以及用户过往的评分数据学习出用户的偏好,最后根据用户的偏好预测其他待评分对象的分数并产生推荐。实验结果表明,提出的方法在预测准确度方面较传统方法有一定程度的提高。     

一种基于用户情境的QoS预测方法

完整的QoS信息有利于更准确的服务推荐,但是现实中往往很难得到。文章提出了一种基于用户情境的QoS预测方法,对于老用户,根据他们原来的QoS选择,考虑QoS类型区别和时间衰减情况,预测新的QoS取值;对于新用户,按照用户分类信息,根据同类用户的服务选择情况,预测他们的QoS取值。实验证明,该方法有助于提高服务推荐的性能。     

A secure dynamic collaboration environment in a cloud context

In recent years, the cloud has emerged as an attractive means for hosting and delivering services over the Internet. This has resulted in a renewed focus on information security in the case where data is stored in the virtual space of the cloud and is not physically accessible to the customer. This paper addresses the increasing security concerns of migrating to the cloud and utilising it for data storage, focusing on securing data in an untrusted cloud environment and ensuring detailed data access control in the cloud. Two Conceptual designs have been devised by exploring and extending the boundaries of existing secure data-storage schemes, and then combining these with well-known security principles and cutting-edge research within the field of cryptography. To further validate the conceptual designs, proof of concept prototypes have been constructed.     

基于用户偏好优化模型的推荐算法研究

传统的个性化推荐算法普遍存在数据稀疏性问题,影响了推荐的准确度。Slope one算法具有简单、高效等特点,但该算法只是根据用户—项目评分矩阵进行数据分析,对所有用户采用一致性的权重进行计算,忽视了用户对项目类型的喜好程度。针对上述问题进行了研究,提出LR-Slope one算法。首先根据用户—项目评分矩阵和项目类型信息构建用户对项目类型的偏好矩阵;然后利用线性回归模型计算用户对每个类型的权重,采用随机梯度下降算法优化权重;最后结合Slope one算法预测评分,填充评分矩阵,提高推荐的质量。实验结果表明,所提算法提高了推荐的精度,有效缓解了稀疏性问题。     

An effective collaborative filtering algorithm based on user preference clustering

Collaborative filtering is one of widely used recommendation approaches to make recommendation services for users. The core of this approach is to improve capability for finding accurate and reliable neighbors of active users. However, collected data is extremely sparse in the user-item rating matrix, meanwhile many existing similarity measure methods using in collaborative filtering are not much effective, which result in the poor performance. In this paper, a novel effective collaborative filtering algorithm based on user preference clustering is proposed to reduce the impact of the data sparsity. First, user groups are introduced to distinguish users with different preferences. Then, considering the preference of the active user, we obtain the nearest neighbor set from corresponding user group/user groups. Besides, a new similarity measure method is proposed to preferably calculate the similarity between users, which considers user preference in the local and global perspectives, respectively. Finally, experimental results on two benchmark data sets show that the proposed algorithm is effective to improve the performance of recommender systems.     

内容中心网络中基于用户偏好的协作缓存策略

针对内容中心网络（CCN）中节点默认缓存所有经过的内容,未能实现对内容选择性缓存与最佳放置的问题,提出一种基于用户偏好的协作缓存策略（CCUP）。首先,考虑用户对内容类型的喜好和内容流行度作为用户本地偏好度指标,实现缓存内容的选择;然后,对需要缓存内容执行差异化缓存策略,全局活跃的内容则缓存在重要的中心节点,非活跃内容则按本地偏好度与节点同用户距离层级匹配缓存;最后,实现用户对本地偏好内容的就近获取和全局活跃内容的快速分发。仿真结果表明,相比典型缓存策略（LCE、Prob（0.6）、Betw）,CCUP在平均缓存命中率和平均请求时延方面有明显优势。